ConvNeXt+YOLOv7改进方案
ConvNeXt理论请参考论文：[2201.03545] A ConvNet for the 2020s (arxiv.org)
yolov7添加CNeB模块代码
1.在 common.py 文件中添加如下代码
class LayerNorm_s(nn.Module):
def __init__(self, normalized_shape, eps=1e-6, data_format="channels_last"):
super().__init__()
self.weight = nn.Parameter(torch.ones(normalized_shape))
self.bias = nn.Parameter(torch.zeros(normalized_shape))
self.eps = eps
self.data_format = data_format
if self.data_format not in ["channels_last", "channels_first"]:
raise NotImplementedError
self.normalized_shape = (normalized_shape,)
def forward(self, x):
if self.data_format == "channels_last":
return F.layer_norm(x, self.normalized_shape, self.weight, self.bias, self.eps)
elif self.data_format == "channels_first":
u = x.mean(1, keepdim=True)
s = (x - u).pow(2).mean(1, keepdim=True)
x = (x - u) / torch.sqrt(s + self.eps)
x = self.weight[:, None, None] * x + self.bias[:, None, None]
return x
class ConvNextBlock(nn.Module):
def __init__(self, dim, drop_path=0., layer_scale_init_value=1e-6):
super().__init__()
self.dwconv = nn.Conv2d(dim, dim, kernel_size=7, padding=3, groups=dim) # depthwise conv
self.norm = LayerNorm_s(dim, eps=1e-6)
self.pwconv1 = nn.Linear(dim, 4 * dim)
self.act = nn.GELU()
self.pwconv2 = nn.Linear(4 * dim, dim)
self.gamma = nn.Parameter(layer_scale_init_value * torch.ones((dim)),
requires_grad=True) if layer_scale_init_value > 0 else None
self.drop_path = DropPath(drop_path) if drop_path > 0. else nn.Identity()
def forward(self, x):
input = x
x = self.dwconv(x)
x = x.permute(0, 2, 3, 1) # (N, C, H, W) -> (N, H, W, C)
x = self.norm(x)
x = self.pwconv1(x)
x = self.act(x)
x = self.pwconv2(x)
if self.gamma is not None:
x = self.gamma * x
x = x.permute(0, 3, 1, 2) # (N, H, W, C) -> (N, C, H, W)
x = input + self.drop_path(x)
return x
class DropPath(nn.Module):
"""Drop paths (Stochastic Depth) per sample (when applied in main path of residual blocks).
"""
def __init__(self, drop_prob=None):
super(DropPath, self).__init__()
self.drop_prob = drop_prob
def forward(self, x):
return drop_path_f(x, self.drop_prob, self.training)
def drop_path_f(x, drop_prob: float = 0., training: bool = False):
if drop_prob == 0. or not training:
return x
keep_prob = 1 - drop_prob
shape = (x.shape[0],) + (1,) * (x.ndim - 1) # work with diff dim tensors, not just 2D ConvNets
random_tensor = keep_prob + torch.rand(shape, dtype=x.dtype, device=x.device)
random_tensor.floor_() # binarize
output = x.div(keep_prob) * random_tensor
return output
class CNeB(nn.Module):
# CSP ConvNextBlock with 3 convolutions by iscyy/yoloair
def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5): # ch_in, ch_out, number, shortcut, groups, expansion
super().__init__()
c_ = int(c2 * e) # hidden channels
self.cv1 = Conv(c1, c_, 1, 1)
self.cv2 = Conv(c1, c_, 1, 1)
self.cv3 = Conv(2 * c_, c2, 1)
self.m = nn.Sequential(*(ConvNextBlock(c_) for _ in range(n)))
def forward(self, x):
return self.cv3(torch.cat((self.m(self.cv1(x)), self.cv2(x)), dim=1))
2.创建yolov7CNEB.yaml配置文件
# YOLOv7 , GPL-3.0 license
# parameters
nc: 80 # number of classes
depth_multiple: 0.33 # 0.55 model depth multiple
width_multiple: 1.0 # 0.55 layer channel multiple
# anchors
anchors:
- [12,16, 19,36, 40,28] # P3/8
- [36,75, 76,55, 72,146] # P4/16
- [142,110, 192,243, 459,401] # P5/32
# yolov7 backbone by yoloair
backbone:
# [from, number, module, args]
[[-1, 1, Conv, [32, 3, 1]], # 0
[-1, 1, Conv, [64, 3, 2]], # 1-P1/2
[-1, 1, Conv, [64, 3, 1]],
[-1, 1, Conv, [128, 3, 2]], # 3-P2/4
[-1, 1, CNeB, [128]],
[-1, 1, Conv, [256, 3, 2]],
[-1, 1, MP, []],
[-1, 1, Conv, [128, 1, 1]],
[-3, 1, Conv, [128, 1, 1]],
[-1, 1, Conv, [128, 3, 2]],
[[-1, -3], 1, Concat, [1]], # 16-P3/8
[-1, 1, Conv, [128, 1, 1]],
[-2, 1, Conv, [128, 1, 1]],
[-1, 1, Conv, [128, 3, 1]],
[-1, 1, Conv, [128, 3, 1]],
[-1, 1, Conv, [128, 3, 1]],
[-1, 1, Conv, [128, 3, 1]],
[[-1, -3, -5, -6], 1, Concat, [1]],
[-1, 1, Conv, [512, 1, 1]],
[-1, 1, MP, []],
[-1, 1, Conv, [256, 1, 1]],
[-3, 1, Conv, [256, 1, 1]],
[-1, 1, Conv, [256, 3, 2]],
[[-1, -3], 1, Concat, [1]],
[-1, 1, Conv, [256, 1, 1]],
[-2, 1, Conv, [256, 1, 1]],
[-1, 1, Conv, [256, 3, 1]],
[-1, 1, Conv, [256, 3, 1]],
[-1, 1, Conv, [256, 3, 1]],
[-1, 1, Conv, [256, 3, 1]],
[[-1, -3, -5, -6], 1, Concat, [1]],
[-1, 1, Conv, [1024, 1, 1]],
[-1, 1, MP, []],
[-1, 1, Conv, [512, 1, 1]],
[-3, 1, Conv, [512, 1, 1]],
[-1, 1, Conv, [512, 3, 2]],
[[-1, -3], 1, Concat, [1]],
[-1, 1, CNeB, [1024]],
[-1, 1, Conv, [256, 3, 1]],
]
# yolov7 head by yoloair
head:
[[-1, 1, SPPCSPC, [512]],
[-1, 1, Conv, [256, 1, 1]],
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
[31, 1, Conv, [256, 1, 1]],
[[-1, -2], 1, Concat, [1]],
[-1, 1, CNeB, [128]],
[-1, 1, Conv, [128, 1, 1]],
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
[18, 1, Conv, [128, 1, 1]],
[[-1, -2], 1, Concat, [1]],
[-1, 1, CNeB, [128]],
[-1, 1, MP, []],
[-1, 1, Conv, [128, 1, 1]],
[-3, 1, Conv, [128, 1, 1]],
[-1, 1, Conv, [128, 3, 2]],
[[-1, -3, 44], 1, Concat, [1]],
[-1, 1, CNeB, [256]],
[-1, 1, MP, []],
[-1, 1, Conv, [256, 1, 1]],
[-3, 1, Conv, [256, 1, 1]],
[-1, 1, Conv, [256, 3, 2]],
[[-1, -3, 39], 1, Concat, [1]],
[-1, 3, CNeB, [512]],
# 检测头 -----------------------------
[49, 1, RepConv, [256, 3, 1]],
[55, 1, RepConv, [512, 3, 1]],
[61, 1, RepConv, [1024, 3, 1]],
[[62,63,64], 1, IDetect, [nc, anchors]], # Detect(P3, P4, P5)
]
3.在 models/yolo.py文件夹下找到parse_model函数
在 for i, (f, n, m, args) in enumerate(d['backbone'] + d['head']):下方添加以下代码
elif m is CNeB:
c1, c2 = ch[f], args[0]
if c2 != no:
c2 = make_divisible(c2 * gw, 8)
args = [c1, c2, *args[1:]]
if m is CNeB:
args.insert(2, n)
n = 1